Visual Geo-localization (VG) is the task of estimating the position where a
given photo was taken by comparing it with a large database of images of known
locations. To investigate how existing techniques would perform on a real-world
city-wide VG application, we build San Francisco eXtra Large, a new dataset
covering a whole city and providing a wide range of challenging cases, with a
size 30x bigger than the previous largest dataset for visual geo-localization.
We find that current methods fail to scale to such large datasets, therefore we
design a new highly scalable training technique, called CosPlace, which casts
the training as a classification problem avoiding the expensive mining needed
by the commonly used contrastive learning. We achieve state-of-the-art
performance on a wide range of datasets and find that CosPlace is robust to
heavy domain changes. Moreover, we show that, compared to the previous
state-of-the-art, CosPlace requires roughly 80% less GPU memory at train time,
and it achieves better results with 8x smaller descriptors, paving the way for
city-wide real-world visual geo-localization. Dataset, code and trained models
are available for research purposes at this https URL

在这篇论文中，我们构建了一个 30 倍于现有最大数据集的 San Francisco eXtra Large 数据集，研究了现有的技术在实际城市范围内的视觉定位应用中的性能表现，并设计了一种高度可扩展的训练技术 CosPlace，它将训练模型作为分类问题，避免了常用对比学习的昂贵挖掘技术，这种技术在多个数据集上均能实现最先进的表现，并且相对于现有技术，它需要的 GPU 内存减少了约 80％，且在描述符更小的情况下取得更好的结果。